Cfn Task Intelligence
Productivitycfn-task-intelligenceCfn Task Intelligence is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Classify tasks (type/domain), estimate complexity/iterations, recommend specialists from feedback themes
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/analysis/cfn-task-intelligence-masharratt-claude-flow-novice-2/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/cfn-task-intelligence, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
What it does
Analyzes task descriptions → classifies type (software, content, research, design, infrastructure, data), detects domains (frontend, backend, security, devops, testing, database, docs), estimates complexity + iterations, recommends specialists from recurring feedback.
When to use
- New task → Determine CFN Loop config and agents
- Estimate iterations → How many loops before gates pass
- Recurring issues → After 3 security feedback, recommend security-specialist
- Multi-agent coordination → Identify domains and dependencies
When NOT to use
- Task already classified → Proceed with execution
- Simple type check → Use /write-plan instead
- Agent failure debugging → Use /cfn-check-errors
- Adjust teams mid-execution → Use /cfn-agent-lifecycle
How to use
Classify: ./cfn-task-intelligence.sh --task-description "..." --mode classify Complexity: --mode complexity (returns iterations 2-7, confidence 0.70-0.80) Specialist: --mode specialist --current-loop3 "..." --feedback-themes "security,auth" --recurring-count 3 Full: --mode all
Parameters
--task-description, --mode (classify/complexity/specialist/all), --current-loop3, --feedback-themes, --recurring-count
Expected output
Classify: {task_type, domains[], complexity, keyword_counts} Complexity: {complexity, estimated_iterations, confidence, factors, reasoning} Specialist: {add_specialist, reasoning, new_loop3_agents[]}
Real-world
"Microservice with K8s and streaming" → infrastructure, [backend,devops,database], high, 6 iterations → spawn DevOps + backend, enterprise mode